Related papers: Variational Autoencoder Learns Better Feature Repr…

There are many problems in physics, biology, and other natural sciences in which symbolic regression can provide valuable insights and discover new laws of nature. A widespread Deep Neural Networks do not provide interpretable solutions.…

Objective: To develop and interpret a supervised variational autoencoder (VAE) model for classifying cardiotocography (CTG) signals based on pregnancy outcomes, addressing interpretability limits of current deep learning approaches.…

The brain age is a key indicator of brain health. While electroencephalography (EEG) is a practical tool for this task, existing models struggle with the common challenge of imperfect medical data, such as learning a ``normal'' baseline…

We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised…

We consider the problem of extracting features from passive, multi-channel electroencephalogram (EEG) devices for downstream inference tasks related to high-level mental states such as stress and cognitive load. Our proposed method…

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this…

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input…

The electrocardiogram (ECG) is an inexpensive and widely available tool for cardiovascular assessment. Despite its standardized format and small file size, the high complexity and inter-individual variability of ECG signals (typically a…

Data-driven fault diagnostics of safety-critical systems often faces the challenge of a complete lack of labeled data associated with faulty system conditions (i.e., fault types) at training time. Since an unknown number and nature of fault…

Objective: Machine learning- and deep learning-based models have recently been employed in motor imagery intention classification from electroencephalogram (EEG) signals. Nevertheless, there is a limited understanding of feature selection…

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…

Convolutional neural networks (CNN) have been frequently used to extract subject-invariant features from electroencephalogram (EEG) for classification tasks. This approach holds the underlying assumption that electrodes are equidistant…

The detection of Alzheimers disease (AD) is considered crucial, as timely intervention can improve patient outcomes. Electroencephalogram (EEG)-based diagnosis has been recognized as a non-invasive, accessible, and cost-effective approach…

We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative…

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a…

In this paper, we aimed at reviewing present literature on employing nonlinear analysis in combination with machine learning methods, in depression detection or prediction task. We are focusing on an affordable data-driven approach,…

We present two deep generative models based on Variational Autoencoders to improve the accuracy of drug response prediction. Our models, Perturbation Variational Autoencoder and its semi-supervised extension, Drug Response Variational…

Self-supervised learning has emerged as a highly effective approach in the fields of natural language processing and computer vision. It is also applicable to brain signals such as electroencephalography (EEG) data, given the abundance of…

EEG signals convey important information about brain activity both in healthy and pathological conditions. However, they are inherently noisy, which poses significant challenges for accurate analysis and interpretation. Traditional EEG…

We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and…